Improving Generalization via Attribute Selection on Out-of-the-box Data

Zero-shot learning (ZSL) aims to recognize unseen objects (test classes) given some other seen objects (training classes), by sharing information of attributes between different objects. Attributes are artificially annotated for objects and are treated equally in recent ZSL tasks. However, some inferior attributes with poor predictability or poor discriminability may have negative impact on the ZSL system performance. This paper first derives a generalization error bound for ZSL tasks. Our theoretical analysis verifies that selecting key attributes set can improve the generalization performance of the original ZSL model which uses all the attributes. Unfortunately, previous attribute selection methods are conducted based on the seen data, their selected attributes have poor generalization capability to the unseen data, which is unavailable in training stage for ZSL tasks. Inspired by learning from pseudo relevance feedback, this paper introduces the out-of-the-box data, which is pseudo data generated by an attribute-guided generative model, to mimic the unseen data. After that, we present an iterative attribute selection (IAS) strategy which iteratively selects key attributes based on the out-of-the-box data. Since the distribution of the generated out-of-the-box data is similar to the test data, the key attributes selected by IAS can be effectively generalized to test data. Extensive experiments demonstrate that IAS can significantly improve existing attribute-based ZSL methods and achieve state-of-the-art performance.

Learning Image-Specific Attributes by Hyperbolic Neighborhood Graph Propagation

As a kind of semantic representation of visual object descriptions, attributes are widely used in various computer vision tasks. In most of existing attribute-based research, class-specific attributes (CSA), which are class-level annotations, are usually adopted due to its low annotation cost for each class instead of each individual image. However, class-specific attributes are usually noisy because of annotation errors and diversity of individual images. Therefore, it is desirable to obtain image-specific attributes (ISA), which are image-level annotations, from the original class-specific attributes. In this paper, we propose to learn image-specific attributes by graph-based attribute propagation. Considering the intrinsic property of hyperbolic geometry that its distance expands exponentially, hyperbolic neighborhood graph (HNG) is constructed to characterize the relationship between samples. Based on HNG, we define neighborhood consistency for each sample to identify inconsistent samples. Subsequently, inconsistent samples are refined based on their neighbors in HNG. Extensive experiments on five benchmark datasets demonstrate the significant superiority of the learned image-specific attributes over the original class-specific attributes in the zero-shot object classification task.

Zero-shot Learning with Complementary Attributes

Zero-shot learning (ZSL) aims to recognize unseen objects using disjoint seen objects via attributes to transfer semantic information from training data to testing data. The generalization performance of ZSL is governed by the attributes, which represent the relatedness between the seen classes and the unseen classes. In this paper, we propose a novel ZSL method using complementary attributes as a supplement to the original attributes. We first expand attributes with their complementary form, and then pre-train classifiers for both original attributes and complementary attributes using training data. After ranking classes for each attribute, we use rank aggregation framework to calculate the optimized rank among testing classes of which the highest order is assigned as the label of testing sample. We empirically demonstrate that complementary attributes have an effective improvement for ZSL models. Experimental results show that our approach outperforms state-of-the-art methods on standard ZSL datasets.